Data analyses
The iNaturalist Network is a localised experience that is fully connected to the global iNaturalist community. Network members are local institutions that promote local use and facilitate the use of data from iNaturalist to benefit local
The aim of this report is to give an account of the importance of the iNaturalist network members by analysing the number of records for each country.
library(httr)
library(jsonlite)
library(knitr)
library(rgbif)
library(ggrepel)
library(extrafont)
library(patchwork)
library(parallel)
library(doParallel)
library(hstats)
library(vip)
library(future)
library(tidymodels)
library(tidyverse)
options(knitr.kable.NA = '')
options(scipen=999)iNat_network <-
tribble(~'site', ~'site_name', ~'site_id',
'Global', 'iNaturalist', 1,
'Mexico', 'iNaturalistMX', 2,
'New Zealand', 'iNaturalistNZ', 3,
'Canada', 'iNaturalist.ca', 5,
'Colombia', 'NaturalistaCO', 6,
'Portugal', 'BioDiversity4All', 8,
'Australia', 'iNaturalistAU', 9,
'Panama', 'iNaturalistPa', 13,
'Ecuador', 'iNaturalistEc', 14,
'Israel', 'iNaturalistil', 15,
'Argentina', 'ArgentiNat', 16,
'Costa Rica', 'NaturalistaCR', 17,
'Chile', 'iNaturalistCL', 18,
'Finland', 'iNaturalistFi', 20,
'Sweeden', 'iNaturalist.Se', 21,
'Spain', 'Natusfera', 22,
'Greece', 'iNaturalistGR', 23,
'Guatemala', 'iNaturalistGT', 24,
'United Kingdom', 'iNaturalistUK', 25,
'Luxembourg', 'iNaturalist.LU', 26,
'Taiwan', 'iNaturalistTW', 27,
'Uruguay', 'NaturalistaUY', 28)
iNat_network %>%
mutate('#'= row_number()) %>% relocate('#') %>%
rename(`Site` = site,
`Name`=site_name,
`ID`=site_id) %>%
kableExtra::kbl(digits=1, format.args = list(big.mark = ',')) %>%
kableExtra::kable_material('striped') %>%
kableExtra::row_spec(row = c(2,5,8,9,11,12,13,18,22), bold = T, color = "white", background = "#228A22")| # | Site | Name | ID |
|---|---|---|---|
| 1 | Global | iNaturalist | 1 |
| 2 | Mexico | iNaturalistMX | 2 |
| 3 | New Zealand | iNaturalistNZ | 3 |
| 4 | Canada | iNaturalist.ca | 5 |
| 5 | Colombia | NaturalistaCO | 6 |
| 6 | Portugal | BioDiversity4All | 8 |
| 7 | Australia | iNaturalistAU | 9 |
| 8 | Panama | iNaturalistPa | 13 |
| 9 | Ecuador | iNaturalistEc | 14 |
| 10 | Israel | iNaturalistil | 15 |
| 11 | Argentina | ArgentiNat | 16 |
| 12 | Costa Rica | NaturalistaCR | 17 |
| 13 | Chile | iNaturalistCL | 18 |
| 14 | Finland | iNaturalistFi | 20 |
| 15 | Sweeden | iNaturalist.Se | 21 |
| 16 | Spain | Natusfera | 22 |
| 17 | Greece | iNaturalistGR | 23 |
| 18 | Guatemala | iNaturalistGT | 24 |
| 19 | United Kingdom | iNaturalistUK | 25 |
| 20 | Luxembourg | iNaturalist.LU | 26 |
| 21 | Taiwan | iNaturalistTW | 27 |
| 22 | Uruguay | NaturalistaUY | 28 |
We tested different explanatory variables and saw which is the model that best explains the values a country has for iNaturalist. Indicators per country were extracted using the WDI: World Development Indicators (World Bank) on the 26th of September, 2025.
Response variables:
n_records_inat.p_gbif.n_users.n_taxa.Explanatory variables:
population (SP.POP.TOTL).area (AG.SRF.TOTL.K2).latitude (using rnaturalearth country polygons).gdp_per_capita (NY.GDP.PCAP.CD).gdp_in_research GB.XPD.RSDV.GD.ZS).Functions
source('R/variables_per_country.R')Data download
UnitedStates <- tibble(country_name= 'United States')
UnitedStates <- UnitedStates %>%
mutate(country_code = countrycode::countrycode(country_name,
origin = 'country.name',
destination = 'iso2c'))
n_inat_gbif_country <- getGBIFrecordsPerCountry(UnitedStates$country_code)
n_inat_country <- getiNatRecordsPerCountry(UnitedStates$country_name)
n_users_country <- getiNatUsersPerCountry(UnitedStates$country_name)
n_taxa_country <- getiNatTaxaPerCountry(UnitedStates$country_name)
area_country <- getAreaPerCountry(UnitedStates$country_code)
population <- getPopulationPerCountry(UnitedStates$country_code)
gdp_per_capita <- getGDPperCapitaPerCountry(UnitedStates$country_code)
gdp_in_research <- getGDPinResearchPerCountry(UnitedStates$country_code)
latitude <- getLatitudePerCountry(UnitedStates$country_code)
data_variables_UnitedStates <- left_join(left_join(left_join(left_join(
left_join(left_join(left_join(left_join(left_join(
UnitedStates, n_inat_gbif_country),
n_inat_country),
n_users_country),
n_taxa_country),
area_country),
population),
gdp_per_capita),
gdp_in_research), latitude)
saveRDS(data_variables_UnitedStates, 'data/UnitedStates_data_variables.rds')
########################################################################
America <- tibble(country_name= c('Canada', 'Mexico', 'Brazil', 'Costa Rica', 'Colombia', 'Peru', 'Argentina', 'Ecuador', 'Panama', 'Chile', 'Venezuela', 'Belize', 'Honduras', 'Bolivia', 'Guatemala', 'Cuba', 'Nicaragua', 'Paraguay', 'Bahamas', 'Jamaica', 'Trinidad and Tobago', 'Guyana', 'Dominican Republic', 'El Salvador', 'Suriname', 'Uruguay', 'Haiti'))
America <- America %>%
mutate(country_code = countrycode::countrycode(country_name,
origin = 'country.name',
destination = 'iso2c'))
America <- left_join(America, iNat_network %>% rename(country_name=site))
n_inat_gbif_country <- getGBIFrecordsPerCountry(America$country_code)
n_inat_country <- getiNatRecordsPerCountry(America$country_name)
n_users_country <- getiNatUsersPerCountry(America$country_name)
n_taxa_country <- getiNatTaxaPerCountry(America$country_name)
area_country <- getAreaPerCountry(America$country_code)
population <- getPopulationPerCountry(America$country_code)
gdp_per_capita <- getGDPperCapitaPerCountry(America$country_code)
gdp_in_research <- getGDPinResearchPerCountry(America$country_code)
latitude <- getLatitudePerCountry(America$country_code)
data_variables_America <- left_join(left_join(left_join(left_join(
left_join(left_join(left_join(left_join(left_join(
America, n_inat_gbif_country),
n_inat_country),
n_users_country),
n_taxa_country),
area_country),
population),
gdp_per_capita),
gdp_in_research), latitude)
saveRDS(data_variables_America, 'data/America_data_variables.rds')
########################################################################
Europe <- tibble(country_name = c('Austria', 'Belgium', 'Bulgaria', 'Croatia', 'Cyprus', 'Czechia', 'Denmark', 'Estonia', 'Finland', 'France', 'Germany', 'Greece', 'Hungary', 'Ireland', 'Italy', 'Latvia', 'Lithuania', 'Luxembourg', 'Malta', 'Netherlands', 'Poland', 'Portugal', 'Romania', 'Slovakia', 'Slovenia', 'Spain', 'Sweden', 'United Kingdom', 'Iceland', 'Liechtenstein', 'Norway', 'Switzerland', 'Albania', 'Bosnia and Herzegovina', 'Georgia', 'Moldova', 'Montenegro', 'Macedonia', 'Serbia', 'Turkey', 'Ukraine'))
Europe <- Europe %>%
mutate(country_code = countrycode::countrycode(country_name,
origin = 'country.name',
destination = 'iso2c'))
Europe <- left_join(Europe, iNat_network %>% rename(country_name=site))
n_inat_gbif_country <- getGBIFrecordsPerCountry(Europe$country_code)
n_inat_country <- getiNatRecordsPerCountry(Europe$country_name)
n_users_country <- getiNatUsersPerCountry(Europe$country_name)
n_taxa_country <- getiNatTaxaPerCountry(Europe$country_name)
area_country <- getAreaPerCountry(Europe$country_code)
population <- getPopulationPerCountry(Europe$country_code)
gdp_per_capita <- getGDPperCapitaPerCountry(Europe$country_code)
gdp_in_research <- getGDPinResearchPerCountry(Europe$country_code)
latitude <- getLatitudePerCountry(Europe$country_code)
data_variables_Europe <- left_join(left_join(left_join(left_join(
left_join(left_join(left_join(left_join(left_join(
Europe, n_inat_gbif_country),
n_inat_country),
n_users_country),
n_taxa_country),
area_country),
population),
gdp_per_capita),
gdp_in_research), latitude)
saveRDS(data_variables_Europe, 'data/Europe_data_variables.rds')
########################################################################
Asia <- tibble(country_name = c('India', 'China', 'Indonesia', 'Pakistan', 'Bangladesh', 'Japan', 'Philippines', 'Vietnam', 'Iran', 'Turkey', 'Thailand', 'Myanmar', 'South Korea','Iraq', 'Afghanistan', 'Yemen', 'Uzbekistan', 'Malaysia', 'Saudi Arabia', 'Nepal', 'North Korea','Syria', 'Sri Lanka','Kazakhstan', 'Cambodia', 'Jordan', 'United Arab Emirates', 'Tajikistan', 'Azerbaijan', 'Israel', 'Laos', 'Turkmenistan', 'Kyrgyzstan', 'Singapore', 'Lebanon', 'Palestine','Oman', 'Kuwait', 'Georgia', 'Mongolia', 'Qatar', 'Armenia', 'Bahrain', 'Timor Leste', 'Cyprus', 'Bhutan', 'Maldives', 'Brunei', 'Taiwan'))
Asia <- Asia %>%
mutate(country_code = countrycode::countrycode(country_name,
origin = 'country.name',
destination = 'iso2c'))
Asia <- left_join(Asia, iNat_network %>% rename(country_name=site))
n_inat_gbif_country <- getGBIFrecordsPerCountry(Asia$country_code)
n_inat_country <- getiNatRecordsPerCountry(Asia$country_name)
n_users_country <- getiNatUsersPerCountry(Asia$country_name)
n_taxa_country <- getiNatTaxaPerCountry(Asia$country_name)
area_country <- getAreaPerCountry(Asia$country_code)
population <- getPopulationPerCountry(Asia$country_code)
gdp_per_capita <- getGDPperCapitaPerCountry(Asia$country_code)
gdp_in_research <- getGDPinResearchPerCountry(Asia$country_code)
latitude <- getLatitudePerCountry(Asia$country_code)
data_variables_Asia <- left_join(left_join(left_join(left_join(
left_join(left_join(left_join(left_join(left_join(
Asia, n_inat_gbif_country),
n_inat_country),
n_users_country),
n_taxa_country),
area_country),
population),
gdp_per_capita),
gdp_in_research), latitude)
data_variables_Asia <- data_variables_Asia %>%
mutate(area = ifelse(country_name == 'Taiwan', 36197, area),
population = ifelse(country_name == 'Taiwan', 23365274, population))
saveRDS(data_variables_Asia, 'data/Asia_data_variables.rds')
########################################################################
Oceania <- tibble(country_name = c('Australia', 'Papua New Guinea', 'New Zealand', 'Fiji', 'Solomon Islands', 'Federated States of Micronesia', 'Vanuatu', 'Samoa', 'Kiribati', 'Tonga', 'Marshall Islands', 'Palau', 'Tuvalu', 'Nauru'))
Oceania <- Oceania %>%
mutate(country_code = countrycode::countrycode(country_name,
origin = 'country.name',
destination = 'iso2c'))
Oceania <- left_join(Oceania, iNat_network %>% rename(country_name=site))
n_inat_gbif_country <- getGBIFrecordsPerCountry(Oceania$country_code)
n_inat_country <- getiNatRecordsPerCountry(Oceania$country_name)
n_users_country <- getiNatUsersPerCountry(Oceania$country_name)
n_taxa_country <- getiNatTaxaPerCountry(Oceania$country_name)
area_country <- getAreaPerCountry(Oceania$country_code)
population <- getPopulationPerCountry(Oceania$country_code)
gdp_per_capita <- getGDPperCapitaPerCountry(Oceania$country_code)
gdp_in_research <- getGDPinResearchPerCountry(Oceania$country_code)
latitude <- getLatitudePerCountry(Oceania$country_code)
data_variables_Oceania <- left_join(left_join(left_join(left_join(
left_join(left_join(left_join(left_join(left_join(
Oceania, n_inat_gbif_country),
n_inat_country),
n_users_country),
n_taxa_country),
area_country),
population),
gdp_per_capita),
gdp_in_research), latitude)
saveRDS(data_variables_Oceania, 'data/Oceania_data_variables.rds')
########################################################################
variables_global <- bind_rows(data_variables_UnitedStates %>%
mutate(continent = 'America'),
data_variables_America %>%
mutate(continent = 'America'),
data_variables_Europe %>%
mutate(continent = 'Europe'),
data_variables_Asia %>%
mutate(continent = 'Asia'),
data_variables_Oceania %>%
mutate(continent = 'Oceania')) %>%
unique()
# variables_global <- bind_rows(readRDS('data/UnitedStates_data_variables.rds') %>%
# mutate(continent = 'America'),
# readRDS('data/America_data_variables.rds') %>%
# mutate(continent = 'America'),
# readRDS('data/Europe_data_variables.rds') %>%
# mutate(continent = 'Europe'),
# readRDS('data/Asia_data_variables.rds') %>%
# mutate(continent = 'Asia'),
# readRDS('data/Oceania_data_variables.rds') %>%
# mutate(continent = 'Oceania')) %>%
# unique()
saveRDS(variables_global, 'data/Global_data_variables.rds')ids <- data_variables %>%
select(country_name,site_name, n_records_inat) %>%
arrange(desc(n_records_inat)) %>%
with(which(!is.na(site_name)))
data_variables %>%
select(country_name,site_name, n_records_inat) %>%
arrange(desc(n_records_inat)) %>%
mutate('#'= row_number()) %>% relocate('#') %>%
rename(`Country` = country_name,
`iNat site` = site_name,
`Records on iNat`=n_records_inat) %>%
kableExtra::kbl(digits=4, format.args = list(big.mark = ',')) %>%
kableExtra::kable_material('striped') %>%
kableExtra::row_spec(ids, bold = T, color = "white", background = "#228A22") %>%
kableExtra::scroll_box(height = '600px')| # | Country | iNat site | Records on iNat |
|---|---|---|---|
| 1 | United States | 117,967,387 | |
| 2 | Canada | iNaturalist.ca | 20,889,613 |
| 3 | Australia | iNaturalistAU | 11,976,616 |
| 4 | Mexico | iNaturalistMX | 8,975,015 |
| 5 | United Kingdom | iNaturalistUK | 8,141,711 |
| 6 | Germany | 6,081,430 | |
| 7 | France | 5,749,959 | |
| 8 | Spain | Natusfera | 5,162,544 |
| 9 | Italy | 4,147,436 | |
| 10 | Taiwan | iNaturalistTW | 4,052,959 |
| 11 | India | 4,013,726 | |
| 12 | Brazil | 3,829,606 | |
| 13 | New Zealand | iNaturalistNZ | 3,148,237 |
| 14 | Austria | 2,935,237 | |
| 15 | Portugal | BioDiversity4All | 2,332,457 |
| 16 | China | 2,042,227 | |
| 17 | Colombia | NaturalistaCO | 2,040,943 |
| 18 | Ecuador | iNaturalistEc | 2,024,022 |
| 19 | Argentina | ArgentiNat | 1,926,013 |
| 20 | Ukraine | 1,875,798 | |
| 21 | Denmark | 1,854,729 | |
| 22 | Costa Rica | NaturalistaCR | 1,764,500 |
| 23 | Poland | 1,584,642 | |
| 24 | Czechia | 1,487,638 | |
| 25 | Finland | iNaturalistFi | 1,424,762 |
| 26 | Japan | 1,156,139 | |
| 27 | Thailand | 1,108,651 | |
| 28 | Malaysia | 1,092,232 | |
| 29 | Netherlands | 1,083,404 | |
| 30 | Indonesia | 1,071,014 | |
| 31 | Switzerland | 1,069,803 | |
| 32 | Chile | iNaturalistCL | 947,995 |
| 33 | Peru | 870,745 | |
| 34 | Bolivia | 838,793 | |
| 35 | Singapore | 824,322 | |
| 36 | Sweden | 814,504 | |
| 37 | Greece | iNaturalistGR | 798,341 |
| 38 | Panama | iNaturalistPa | 754,561 |
| 39 | Belgium | 726,270 | |
| 40 | South Korea | 611,801 | |
| 41 | Hungary | 584,655 | |
| 42 | Lithuania | 526,786 | |
| 43 | Philippines | 514,868 | |
| 44 | Croatia | 511,726 | |
| 45 | Norway | 437,397 | |
| 46 | Turkey | 426,156 | |
| 47 | Turkey | 426,156 | |
| 48 | Luxembourg | iNaturalist.LU | 416,368 |
| 49 | Israel | iNaturalistil | 385,310 |
| 50 | Honduras | 357,290 | |
| 51 | Ireland | 329,796 | |
| 52 | Romania | 320,947 | |
| 53 | Slovakia | 285,607 | |
| 54 | Kazakhstan | 252,847 | |
| 55 | Slovenia | 244,685 | |
| 56 | Sri Lanka | 226,260 | |
| 57 | Vietnam | 221,263 | |
| 58 | Bulgaria | 198,429 | |
| 59 | Georgia | 184,488 | |
| 60 | Georgia | 184,488 | |
| 61 | Guatemala | iNaturalistGT | 181,281 |
| 62 | Belize | 169,354 | |
| 63 | Uruguay | NaturalistaUY | 164,832 |
| 64 | Serbia | 158,850 | |
| 65 | Dominican Republic | 154,161 | |
| 66 | Iceland | 148,739 | |
| 67 | Trinidad and Tobago | 140,844 | |
| 68 | Nicaragua | 131,036 | |
| 69 | Nepal | 130,339 | |
| 70 | Mongolia | 115,092 | |
| 71 | Venezuela | 103,603 | |
| 72 | El Salvador | 98,296 | |
| 73 | Cuba | 91,235 | |
| 74 | Estonia | 89,338 | |
| 75 | Cambodia | 89,117 | |
| 76 | Latvia | 88,631 | |
| 77 | Albania | 82,935 | |
| 78 | Armenia | 78,661 | |
| 79 | Jamaica | 78,158 | |
| 80 | Cyprus | 77,430 | |
| 81 | Cyprus | 77,430 | |
| 82 | United Arab Emirates | 76,021 | |
| 83 | Fiji | 74,285 | |
| 84 | Montenegro | 73,202 | |
| 85 | Maldives | 69,967 | |
| 86 | Iran | 67,337 | |
| 87 | Bahamas | 64,650 | |
| 88 | Uzbekistan | 53,515 | |
| 89 | Bosnia and Herzegovina | 52,898 | |
| 90 | Bhutan | 52,621 | |
| 91 | Kyrgyzstan | 47,691 | |
| 92 | Pakistan | 42,750 | |
| 93 | Paraguay | 41,175 | |
| 94 | Papua New Guinea | 40,484 | |
| 95 | Bangladesh | 40,082 | |
| 96 | Myanmar | 34,611 | |
| 97 | Palestine | 34,110 | |
| 98 | Saudi Arabia | 32,759 | |
| 99 | Oman | 32,143 | |
| 100 | Suriname | 31,834 | |
| 101 | Guyana | 30,510 | |
| 102 | Malta | 30,143 | |
| 103 | Macedonia | 29,846 | |
| 104 | Kuwait | 29,436 | |
| 105 | Laos | 28,762 | |
| 106 | Vanuatu | 25,780 | |
| 107 | Syria | 25,686 | |
| 108 | Marshall Islands | 24,770 | |
| 109 | Jordan | 22,791 | |
| 110 | Azerbaijan | 21,364 | |
| 111 | Palau | 21,237 | |
| 112 | Haiti | 17,040 | |
| 113 | Moldova | 16,802 | |
| 114 | Iraq | 15,958 | |
| 115 | Solomon Islands | 15,829 | |
| 116 | Lebanon | 15,320 | |
| 117 | Brunei | 13,443 | |
| 118 | Tajikistan | 12,286 | |
| 119 | Qatar | 11,253 | |
| 120 | Yemen | 9,948 | |
| 121 | Tonga | 8,488 | |
| 122 | Federated States of Micronesia | 6,372 | |
| 123 | Samoa | 5,917 | |
| 124 | Liechtenstein | 5,667 | |
| 125 | Bahrain | 3,656 | |
| 126 | Tuvalu | 2,968 | |
| 127 | Kiribati | 2,585 | |
| 128 | North Korea | 2,143 | |
| 129 | Afghanistan | 1,450 | |
| 130 | Turkmenistan | 662 | |
| 131 | Nauru | 103 | |
| 132 | Timor Leste |
ids <- data_variables %>%
select(country_name, site_name, n_records_gbif, n_records_gbif_inat) %>%
mutate(p_gbif=n_records_gbif_inat*100/n_records_gbif) %>%
arrange(desc(p_gbif)) %>%
with(which(!is.na(site_name)))
data_variables %>%
select(country_name, site_name, n_records_gbif, n_records_gbif_inat) %>%
mutate(p_gbif=n_records_gbif_inat*100/n_records_gbif) %>%
arrange(desc(p_gbif)) %>%
mutate('#'= row_number()) %>% relocate('#') %>%
select(-n_records_gbif_inat) %>%
rename(`Country` = country_name,
`iNat site` = site_name,
`Records from iNat on GBIF`=n_records_gbif,
`Proportion`=p_gbif) %>%
kableExtra::kbl(digits=4, format.args = list(big.mark = ',')) %>%
kableExtra::kable_material('striped') %>%
kableExtra::row_spec(ids, bold = T, color = "white", background = "#228A22") %>%
kableExtra::scroll_box(height = '600px')| # | Country | iNat site | Records from iNat on GBIF | Proportion |
|---|---|---|---|---|
| 1 | Maldives | 108,822 | 28.6808 | |
| 2 | Ukraine | 3,931,831 | 27.5579 | |
| 3 | Albania | 144,430 | 22.7903 | |
| 4 | Italy | 8,596,699 | 21.9913 | |
| 5 | Kazakhstan | 539,075 | 21.7589 | |
| 6 | Singapore | 1,974,945 | 20.2467 | |
| 7 | Croatia | 1,274,969 | 19.0917 | |
| 8 | Tuvalu | 9,776 | 18.9546 | |
| 9 | Montenegro | 174,675 | 18.8745 | |
| 10 | Bosnia and Herzegovina | 98,561 | 17.4674 | |
| 11 | Malta | 99,495 | 16.9767 | |
| 12 | Lithuania | 1,479,823 | 16.4623 | |
| 13 | Uzbekistan | 148,530 | 15.3498 | |
| 14 | Fiji | 307,778 | 14.7860 | |
| 15 | Hungary | 2,226,224 | 13.2507 | |
| 16 | Marshall Islands | 120,862 | 13.0322 | |
| 17 | Czechia | 5,318,179 | 11.9122 | |
| 18 | Slovenia | 921,600 | 11.8601 | |
| 19 | New Zealand | iNaturalistNZ | 16,738,367 | 11.7287 |
| 20 | Indonesia | 3,461,778 | 11.7265 | |
| 21 | Austria | 15,651,302 | 11.1046 | |
| 22 | Timor Leste | 97,706 | 11.0812 | |
| 23 | Greece | iNaturalistGR | 4,019,188 | 10.3777 |
| 24 | Mexico | iNaturalistMX | 35,031,471 | 9.9170 |
| 25 | Armenia | 242,972 | 9.8859 | |
| 26 | Romania | 1,476,087 | 9.8087 | |
| 27 | Iraq | 76,252 | 9.5447 | |
| 28 | Mongolia | 682,658 | 8.5092 | |
| 29 | Malaysia | 3,807,247 | 8.0152 | |
| 30 | Slovakia | 1,921,795 | 7.7925 | |
| 31 | Cyprus | 647,634 | 7.1392 | |
| 32 | Cyprus | 647,634 | 7.1392 | |
| 33 | Kyrgyzstan | 253,585 | 6.9630 | |
| 34 | Brunei | 56,851 | 6.8301 | |
| 35 | Luxembourg | iNaturalist.LU | 3,410,536 | 6.6802 |
| 36 | Taiwan | iNaturalistTW | 24,746,071 | 6.6399 |
| 37 | Vietnam | 976,607 | 6.6174 | |
| 38 | Dominican Republic | 929,637 | 6.5430 | |
| 39 | Argentina | ArgentiNat | 17,173,754 | 6.5071 |
| 40 | Macedonia | 169,132 | 6.5008 | |
| 41 | Vanuatu | 174,557 | 6.3601 | |
| 42 | Bahrain | 27,185 | 6.2203 | |
| 43 | Philippines | 2,461,357 | 5.7149 | |
| 44 | Jordan | 169,041 | 5.6986 | |
| 45 | Japan | 9,498,086 | 5.4946 | |
| 46 | Solomon Islands | 195,781 | 5.3274 | |
| 47 | Thailand | 7,522,142 | 5.2464 | |
| 48 | China | 10,802,967 | 5.1972 | |
| 49 | Palau | 216,168 | 5.1585 | |
| 50 | Portugal | BioDiversity4All | 21,577,985 | 5.1444 |
| 51 | Canada | iNaturalist.ca | 208,431,531 | 4.9375 |
| 52 | Georgia | 1,331,321 | 4.8151 | |
| 53 | Georgia | 1,331,321 | 4.8151 | |
| 54 | Yemen | 132,460 | 4.7743 | |
| 55 | Moldova | 131,574 | 4.7418 | |
| 56 | Samoa | 52,369 | 4.7280 | |
| 57 | United States | 1,204,974,260 | 4.4846 | |
| 58 | Serbia | 1,587,635 | 4.4378 | |
| 59 | Uruguay | NaturalistaUY | 2,015,742 | 4.4319 |
| 60 | Poland | 16,895,227 | 4.3893 | |
| 61 | Germany | 72,867,701 | 4.3444 | |
| 62 | Trinidad and Tobago | 1,301,259 | 4.2251 | |
| 63 | Myanmar | 355,497 | 4.1578 | |
| 64 | Ecuador | iNaturalistEc | 13,906,504 | 4.0896 |
| 65 | Turkey | 4,032,089 | 4.0353 | |
| 66 | Turkey | 4,032,089 | 4.0353 | |
| 67 | Sri Lanka | 2,686,470 | 4.0267 | |
| 68 | Bulgaria | 2,740,526 | 3.9647 | |
| 69 | Bolivia | 2,492,127 | 3.9480 | |
| 70 | Haiti | 196,871 | 3.8284 | |
| 71 | South Korea | 5,804,212 | 3.7333 | |
| 72 | Jamaica | 774,333 | 3.6586 | |
| 73 | Latvia | 893,275 | 3.5520 | |
| 74 | Azerbaijan | 261,891 | 3.4881 | |
| 75 | Brazil | 31,933,725 | 3.4878 | |
| 76 | Kuwait | 344,029 | 3.4494 | |
| 77 | Iran | 950,287 | 3.3573 | |
| 78 | Laos | 275,575 | 3.3534 | |
| 79 | Australia | iNaturalistAU | 185,062,276 | 3.3334 |
| 80 | Qatar | 163,536 | 3.2482 | |
| 81 | Honduras | 3,804,522 | 3.1315 | |
| 82 | Chile | iNaturalistCL | 12,329,845 | 3.1303 |
| 83 | Tonga | 136,819 | 3.1297 | |
| 84 | Tajikistan | 95,908 | 3.1259 | |
| 85 | Spain | Natusfera | 80,295,996 | 3.0978 |
| 86 | North Korea | 48,412 | 3.0178 | |
| 87 | Syria | 317,170 | 2.9924 | |
| 88 | Bahamas | 1,099,589 | 2.9905 | |
| 89 | Iceland | 2,535,418 | 2.9310 | |
| 90 | Palestine | 625,030 | 2.8528 | |
| 91 | Liechtenstein | 97,620 | 2.6695 | |
| 92 | Suriname | 517,131 | 2.6444 | |
| 93 | Cambodia | 1,151,596 | 2.6385 | |
| 94 | Panama | iNaturalistPa | 9,429,490 | 2.6022 |
| 95 | Lebanon | 188,865 | 2.5997 | |
| 96 | Nicaragua | 2,282,549 | 2.5558 | |
| 97 | Cuba | 2,123,735 | 2.5539 | |
| 98 | Saudi Arabia | 596,198 | 2.5173 | |
| 99 | El Salvador | 1,424,122 | 2.4690 | |
| 100 | United Kingdom | iNaturalistUK | 197,099,118 | 2.2427 |
| 101 | Peru | 10,594,413 | 2.2321 | |
| 102 | Bangladesh | 760,745 | 2.1922 | |
| 103 | Nepal | 1,718,650 | 2.1773 | |
| 104 | Ireland | 6,772,745 | 2.0821 | |
| 105 | Oman | 679,607 | 2.0247 | |
| 106 | Israel | iNaturalistil | 8,032,039 | 1.9720 |
| 107 | Federated States of Micronesia | 142,767 | 1.9528 | |
| 108 | Bhutan | 733,994 | 1.9224 | |
| 109 | India | 63,405,406 | 1.8926 | |
| 110 | Switzerland | 30,787,704 | 1.7614 | |
| 111 | Costa Rica | NaturalistaCR | 36,438,909 | 1.7524 |
| 112 | United Arab Emirates | 1,962,937 | 1.6571 | |
| 113 | Pakistan | 642,528 | 1.6158 | |
| 114 | France | 197,318,563 | 1.3854 | |
| 115 | Colombia | NaturalistaCO | 37,891,906 | 1.3592 |
| 116 | Finland | iNaturalistFi | 49,609,714 | 1.1837 |
| 117 | Guyana | 974,642 | 1.1344 | |
| 118 | Guatemala | iNaturalistGT | 5,309,889 | 1.1294 |
| 119 | Kiribati | 164,863 | 1.1167 | |
| 120 | Denmark | 64,142,234 | 1.1047 | |
| 121 | Turkmenistan | 24,320 | 1.0938 | |
| 122 | Belize | 7,607,205 | 1.0104 | |
| 123 | Papua New Guinea | 1,823,607 | 0.9176 | |
| 124 | Paraguay | 1,550,251 | 0.8068 | |
| 125 | Belgium | 41,453,454 | 0.8050 | |
| 126 | Nauru | 4,889 | 0.7773 | |
| 127 | Venezuela | 5,110,477 | 0.7244 | |
| 128 | Afghanistan | 69,158 | 0.6651 | |
| 129 | Estonia | 8,660,767 | 0.5359 | |
| 130 | Netherlands | 131,925,688 | 0.3926 | |
| 131 | Norway | 57,721,199 | 0.3669 | |
| 132 | Sweden | 148,209,998 | 0.2440 |
ids <- data_variables %>%
select(country_name, site_name, n_users) %>%
arrange(desc(n_users)) %>%
with(which(!is.na(site_name)))
data_variables %>%
select(country_name, site_name, n_users) %>%
arrange(desc(n_users)) %>%
mutate('#'= row_number()) %>% relocate('#') %>%
rename(`Country` = country_name,
`iNat site` = site_name,
`Users recording on iNat`=n_users) %>%
kableExtra::kbl(digits=4, format.args = list(big.mark = ',')) %>%
kableExtra::kable_material('striped') %>%
kableExtra::row_spec(ids, bold = T, color = "white", background = "#228A22") %>%
kableExtra::scroll_box(height = '600px')| # | Country | iNat site | Users recording on iNat |
|---|---|---|---|
| 1 | United States | 1,934,413 | |
| 2 | Canada | iNaturalist.ca | 271,433 |
| 3 | Mexico | iNaturalistMX | 176,834 |
| 4 | United Kingdom | iNaturalistUK | 157,683 |
| 5 | France | 138,493 | |
| 6 | Australia | iNaturalistAU | 125,027 |
| 7 | Italy | 94,972 | |
| 8 | Germany | 89,923 | |
| 9 | Spain | Natusfera | 82,474 |
| 10 | Denmark | 77,749 | |
| 11 | Brazil | 74,949 | |
| 12 | Taiwan | iNaturalistTW | 61,961 |
| 13 | Colombia | NaturalistaCO | 58,511 |
| 14 | India | 51,941 | |
| 15 | New Zealand | iNaturalistNZ | 48,690 |
| 16 | Portugal | BioDiversity4All | 39,586 |
| 17 | Ecuador | iNaturalistEc | 38,941 |
| 18 | Costa Rica | NaturalistaCR | 38,826 |
| 19 | Czechia | 36,676 | |
| 20 | Austria | 32,866 | |
| 21 | Netherlands | 32,226 | |
| 22 | Finland | iNaturalistFi | 31,699 |
| 23 | Bolivia | 28,519 | |
| 24 | Belgium | 26,335 | |
| 25 | Japan | 25,935 | |
| 26 | Argentina | ArgentiNat | 25,924 |
| 27 | Thailand | 24,844 | |
| 28 | Switzerland | 24,368 | |
| 29 | Indonesia | 24,235 | |
| 30 | Chile | iNaturalistCL | 24,136 |
| 31 | Greece | iNaturalistGR | 23,869 |
| 32 | Sweden | 21,803 | |
| 33 | Poland | 19,909 | |
| 34 | China | 19,896 | |
| 35 | Malaysia | 19,822 | |
| 36 | Peru | 18,321 | |
| 37 | Panama | iNaturalistPa | 18,283 |
| 38 | Philippines | 16,941 | |
| 39 | Turkey | 15,141 | |
| 40 | Turkey | 15,141 | |
| 41 | Croatia | 14,978 | |
| 42 | Ireland | 14,816 | |
| 43 | Norway | 14,728 | |
| 44 | Ukraine | 13,752 | |
| 45 | Singapore | 10,948 | |
| 46 | Lithuania | 9,841 | |
| 47 | Honduras | 9,453 | |
| 48 | South Korea | 8,963 | |
| 49 | Guatemala | iNaturalistGT | 8,398 |
| 50 | Hungary | 8,120 | |
| 51 | Iceland | 7,696 | |
| 52 | Slovenia | 7,537 | |
| 53 | Luxembourg | iNaturalist.LU | 7,319 |
| 54 | Romania | 6,973 | |
| 55 | Vietnam | 6,760 | |
| 56 | Israel | iNaturalistil | 6,646 |
| 57 | Dominican Republic | 6,551 | |
| 58 | Slovakia | 6,426 | |
| 59 | Belize | 4,976 | |
| 60 | Sri Lanka | 4,706 | |
| 61 | Bahamas | 4,523 | |
| 62 | United Arab Emirates | 4,331 | |
| 63 | Uruguay | NaturalistaUY | 4,196 |
| 64 | Georgia | 4,023 | |
| 65 | Georgia | 4,023 | |
| 66 | Bulgaria | 3,947 | |
| 67 | Kazakhstan | 3,568 | |
| 68 | Nepal | 3,476 | |
| 69 | Jamaica | 3,341 | |
| 70 | Nicaragua | 3,177 | |
| 71 | El Salvador | 3,112 | |
| 72 | Estonia | 3,111 | |
| 73 | Cuba | 2,860 | |
| 74 | Serbia | 2,728 | |
| 75 | Cyprus | 2,690 | |
| 76 | Cyprus | 2,690 | |
| 77 | Latvia | 2,622 | |
| 78 | Cambodia | 2,576 | |
| 79 | Montenegro | 2,503 | |
| 80 | Venezuela | 2,481 | |
| 81 | Trinidad and Tobago | 2,460 | |
| 82 | Albania | 2,220 | |
| 83 | Fiji | 1,879 | |
| 84 | Malta | 1,869 | |
| 85 | Maldives | 1,705 | |
| 86 | Bosnia and Herzegovina | 1,691 | |
| 87 | Pakistan | 1,664 | |
| 88 | Bhutan | 1,566 | |
| 89 | Armenia | 1,563 | |
| 90 | Iran | 1,499 | |
| 91 | Mongolia | 1,472 | |
| 92 | Saudi Arabia | 1,421 | |
| 93 | Paraguay | 1,394 | |
| 94 | Laos | 1,348 | |
| 95 | Myanmar | 1,325 | |
| 96 | Jordan | 1,317 | |
| 97 | Macedonia | 1,220 | |
| 98 | Palestine | 1,133 | |
| 99 | Kyrgyzstan | 1,132 | |
| 100 | Oman | 1,107 | |
| 101 | Uzbekistan | 1,097 | |
| 102 | Bangladesh | 1,044 | |
| 103 | Azerbaijan | 815 | |
| 104 | Lebanon | 748 | |
| 105 | Papua New Guinea | 748 | |
| 106 | Guyana | 653 | |
| 107 | Vanuatu | 536 | |
| 108 | Suriname | 525 | |
| 109 | Qatar | 503 | |
| 110 | Brunei | 482 | |
| 111 | Moldova | 457 | |
| 112 | Haiti | 450 | |
| 113 | Liechtenstein | 448 | |
| 114 | Palau | 448 | |
| 115 | Iraq | 401 | |
| 116 | Federated States of Micronesia | 367 | |
| 117 | Tajikistan | 339 | |
| 118 | Kuwait | 339 | |
| 119 | Bahrain | 299 | |
| 120 | Solomon Islands | 291 | |
| 121 | Samoa | 237 | |
| 122 | Tonga | 197 | |
| 123 | Syria | 186 | |
| 124 | Yemen | 145 | |
| 125 | Afghanistan | 136 | |
| 126 | Marshall Islands | 93 | |
| 127 | North Korea | 92 | |
| 128 | Turkmenistan | 91 | |
| 129 | Kiribati | 43 | |
| 130 | Tuvalu | 31 | |
| 131 | Nauru | 11 | |
| 132 | Timor Leste |
## records
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(population/100000, n_records_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Population of the country (hundred thousand)',
y='Number of records on iNaturalist (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records in GBIF
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(population/100000, n_records_gbif_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Population of the country (hundred thousand)',
y='Number of iNat records on GBIF (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## users
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(population/100000, n_users, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', col= 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Population of the country (hundred thousand)',
y='Number of users recording on iNaturalist') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(area/1000,n_records_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Area of the country (thousand km2)',
y='Number of records on iNaturalist (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records in gbif
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(area/1000, n_records_gbif_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Area of the country (thousand km2)',
y='Number of iNat records on GBIF (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## users
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(area/1000, n_users, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Area of the country (thousand km2)',
y='Number of users recording on iNaturalist') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(abs(latitude), n_records_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Absolute decimal latitude of the country\'s centroid',
y='Number of records on iNaturalist (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records in gbif
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(abs(latitude), n_records_gbif_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Absolute decimal latitude of the country\'s centroid',
y='Number of iNat records on GBIF (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## users
ggplot(data_variables %>%
mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(abs(latitude), n_users, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='Absolute decimal latitude of the country\'s centroid',
y='Number of users recording on iNaturalist') +
#scale_x_log10() +
scale_y_log10() +
theme_bw()
## records
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(gdp_per_capita/1000, n_records_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='GDP per capita (thousand USD)',
y='Number of records on iNaturalist (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records in gbif
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(gdp_per_capita/1000, n_records_gbif_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='GDP per capita (thousand USD)',
y='Number of iNat records on GBIF (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## users
ggplot(data_variables %>%
mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(gdp_per_capita/1000, n_users, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='GDP per capita (thousand USD)',
y='Number of users recording on iNaturalist') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(gdp_in_research, n_records_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='GDP of the country dedicated to research (%)',
y='Number of records on iNaturalist (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## records in gbif
ggplot(data_variables %>% mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(gdp_in_research, n_records_gbif_inat/1000, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='GDP of the country dedicated to research (%)',
y='Number of iNat records on GBIF (thousand)') +
scale_x_log10() + scale_y_log10() +
theme_bw()
## users
ggplot(data_variables %>%
mutate(site_on_iNat = ifelse(!is.na(site_id), 'yes', 'no')),
aes(gdp_in_research,n_users, label = site_name)) +
geom_point(aes(col=site_on_iNat), size=2, show.legend = F) +
scale_color_manual(values = c('black', '#74AC00')) +
geom_smooth(method='lm', colour = 'black') +
geom_label_repel(aes(fill=site_on_iNat),
colour = "black", #fontface = "bold",
segment.color = 'black',
show.legend = F, max.overlaps= Inf) +
scale_fill_manual(values = c('#F7F7F7', '#74AC00')) +
labs(x='GDP of the country dedicated to research (%)',
y='Number of users recording on iNaturalist') +
scale_x_log10() + scale_y_log10() +
theme_bw()
data_regressions <- data_variables %>%
filter(country_code != 'US') %>%
mutate(has_site = ifelse(!is.na(site_name), 1, 0)) %>%
mutate(p_gbif = n_records_gbif_inat/n_records_inat) %>%
select(country_code, n_records_inat, p_gbif, n_users, n_taxa,
area, gdp_per_capita, gdp_in_research,
population, latitude, has_site) %>%
filter(!is.na(gdp_in_research) & !is.na(latitude))
###
data_regressions %>%
select(area, gdp_per_capita, gdp_in_research,
population, latitude, has_site) %>%
cor() %>%
kableExtra::kbl(digits=3, format.args = list(big.mark = ',')) %>%
kableExtra::kable_material('striped') | area | gdp_per_capita | gdp_in_research | population | latitude | has_site | |
|---|---|---|---|---|---|---|
| area | 1.000 | 0.020 | 0.072 | 0.423 | -0.106 | 0.196 |
| gdp_per_capita | 0.020 | 1.000 | 0.585 | -0.143 | 0.355 | 0.185 |
| gdp_in_research | 0.072 | 0.585 | 1.000 | 0.068 | 0.359 | 0.126 |
| population | 0.423 | -0.143 | 0.068 | 1.000 | -0.037 | -0.078 |
| latitude | -0.106 | 0.355 | 0.359 | -0.037 | 1.000 | -0.308 |
| has_site | 0.196 | 0.185 | 0.126 | -0.078 | -0.308 | 1.000 |
source('R/random_forest_iNat.R')rf_n_records <- model_iNat_RF(data_df = data_regressions,
explanatory_variable = 'n_records_inat',
skip_vars = c('p_gbif',
'n_users',
'n_taxa'))Time difference of 1.476133 secs# tuning
rf_n_records[[1]]
# observed vs predicted
rf_n_records[[2]]
# variable importance
rf_n_records[[3]]
ggsave(rf_n_records[[3]], filename='figs/variable_importance_n_records.png', device = 'png', dpi = 300, width = 8, height = 5)
# partial plots
rf_n_records[[4]]
ggsave(rf_n_records[[4]], filename='figs/partial_plots_n_records.png', device = 'png', dpi = 300, width = 8, height = 5)
# final model metrics
rf_n_records[[5]] %>%
select(dataset, rsq=.estimate) %>%
mutate(rsq = round(rsq, 3)) %>%
rename(`R^2` = rsq) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| dataset | R^2 |
|---|---|
| train | 0.954 |
| test | 0.786 |
# variable importance
rf_n_records[[6]] %>%
select(Variable, Importance=standardise_Importance) %>%
mutate(Importance = round(Importance, 3)) %>%
rename(`Portion of R^2` = Importance) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| Variable | Portion of R^2 |
|---|---|
| area | 0.192 |
| population | 0.135 |
| latitude | 0.131 |
| gdp_per_capita | 0.120 |
| gdp_in_research | 0.117 |
| has_site | 0.091 |
rf_p_gbif <- model_iNat_RF(data_df = data_regressions,
explanatory_variable = 'p_gbif',
skip_vars = c('n_records_inat',
'n_users',
'n_taxa'))Time difference of 1.101691 secs# tuning
rf_p_gbif[[1]]
# observed vs predicted
rf_p_gbif[[2]]
# variable importance
rf_p_gbif[[3]]
ggsave(rf_p_gbif[[3]], filename='figs/variable_importance_p_gbif.png', device = 'png', dpi = 300, width = 8, height = 5)
# partial plots
rf_p_gbif[[4]]
ggsave(rf_p_gbif[[4]], filename='figs/partial_plots_p_gbif.png', device = 'png', dpi = 300, width = 8, height = 5)
# final model metrics
rf_p_gbif[[5]] %>%
select(dataset, rsq=.estimate) %>%
mutate(rsq = round(rsq, 3)) %>%
rename(`R^2` = rsq) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| dataset | R^2 |
|---|---|
| train | 0.909 |
| test | 0.219 |
# variable importance
rf_p_gbif[[6]] %>%
select(Variable, Importance=standardise_Importance) %>%
mutate(Importance = round(Importance, 3)) %>%
rename(`Portion of R^2` = Importance) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| Variable | Portion of R^2 |
|---|---|
| gdp_per_capita | 0.058 |
| gdp_in_research | 0.047 |
| latitude | 0.042 |
| population | 0.035 |
| area | 0.032 |
| has_site | 0.006 |
rf_n_users <- model_iNat_RF(data_df = data_regressions,
explanatory_variable = 'n_users',
skip_vars = c('n_records_inat',
'p_gbif',
'n_taxa'))Time difference of 1.114389 secs# tuning
rf_n_users[[1]]
# observed vs predicted
rf_n_users[[2]]
# variable importance
rf_n_users[[3]]
ggsave(rf_n_users[[3]], filename='figs/variable_importance_n_users.png', device = 'png', dpi = 300, width = 8, height = 5)
# partial plots
rf_n_users[[4]]
ggsave(rf_n_users[[4]], filename='figs/partial_plots_n_users.png', device = 'png', dpi = 300, width = 8, height = 5)
# final model metrics
rf_n_users[[5]] %>%
select(dataset, rsq=.estimate) %>%
mutate(rsq = round(rsq, 3)) %>%
rename(`R^2` = rsq) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| dataset | R^2 |
|---|---|
| train | 0.949 |
| test | 0.521 |
# variable importance
rf_n_users[[6]] %>%
select(Variable, Importance=standardise_Importance) %>%
mutate(Importance = round(Importance, 3)) %>%
rename(`Portion of R^2` = Importance) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| Variable | Portion of R^2 |
|---|---|
| population | 0.107 |
| area | 0.105 |
| gdp_in_research | 0.087 |
| gdp_per_capita | 0.082 |
| latitude | 0.075 |
| has_site | 0.065 |
rf_n_taxa <- model_iNat_RF(data_df = data_regressions,
explanatory_variable = 'n_taxa',
skip_vars = c('n_records_inat',
'p_gbif',
'n_users'))Time difference of 1.156683 secs# tuning
rf_n_taxa[[1]]
# observed vs predicted
rf_n_taxa[[2]]
# variable importance
rf_n_taxa[[3]]
ggsave(rf_n_taxa[[3]], filename='figs/variable_importance_n_taxa.png', device = 'png', dpi = 300, width = 8, height = 5)
# partial plots
rf_n_taxa[[4]]
ggsave(rf_n_taxa[[4]], filename='figs/partial_plots_n_taxa.png', device = 'png', dpi = 300, width = 8, height = 5)
# final model metrics
rf_n_taxa[[5]] %>%
select(dataset, rsq=.estimate) %>%
mutate(rsq = round(rsq, 3)) %>%
rename(`R^2` = rsq) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| dataset | R^2 |
|---|---|
| train | 0.937 |
| test | 0.782 |
# variable importance
rf_n_taxa[[6]] %>%
select(Variable, Importance=standardise_Importance) %>%
mutate(Importance = round(Importance, 3)) %>%
rename(`Portion of R^2` = Importance) %>%
knitr::kable() %>% kableExtra::kable_styling(bootstrap_options = c("striped", "hover"))| Variable | Portion of R^2 |
|---|---|
| population | 0.185 |
| area | 0.160 |
| gdp_in_research | 0.122 |
| latitude | 0.119 |
| has_site | 0.100 |
| gdp_per_capita | 0.096 |